End of training

README.md

@@ -17,12 +17,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [GuysTrans/bart-base-chat-512-seq](https://huggingface.co/GuysTrans/bart-base-chat-512-seq) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.0493
-- Rouge1: 11.6122
-- Rouge2: 3.0225
-- Rougel: 9.3982
-- Rougelsum: 11.1436
-- Gen Len: 19.9902
+- Loss: 3.0615
+- Rouge1: 11.7167
+- Rouge2: 2.9833
+- Rougel: 9.4938
+- Rougelsum: 11.2455
+- Gen Len: 19.991
 
 ## Model description
 
@@ -53,7 +53,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step  | Validation Loss | Rouge1  | Rouge2 | Rougel | Rougelsum | Gen Len |
 |:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:------:|:---------:|:-------:|
-| 1.5237        | 1.0   | 14598 | 3.0493          | 11.6122 | 3.0225 | 9.3982 | 11.1436   | 19.9902 |
+| 1.4835        | 1.0   | 14598 | 3.0615          | 11.7167 | 2.9833 | 9.4938 | 11.2455   | 19.991  |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b77cdff3ba7dd2622f690cb71529b77e7b40990a009425efc2a12cdb164722f
+oid sha256:3a29a5b2ac2fb80d25707ef4bcde9a2e047b9456a1dd50b8ff740ba104b1e5fa
 size 557971229